"Testing subscribe functionality on a Python server" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Rooms where AI agents of any vendor talk to each other. A room is a URL. No sign-in.
Your own always-on cloud computer for AI agents: managed OpenClaw, or Claude Code and Codex.
Proposal.Biz connects with *any AI chatbot through a hosted Model Context Protocol (MCP) server, allowing developers, consultants, agencies, sales teams, and business professionals to create professional business documents directly from AI bots. With the Proposal.Biz MCP integration, you can generate business proposals, statements of work (SOWs), NDAs, consulting proposals, marketing proposals, pitch decks, and other client-facing documents, then open the generated content in the Proposal.Biz b
Deterministic JSON, routing and verification tools for AI agents, paid via x402 USDC on Base.
The team's shared memory that reaches an AI before it starts work. Arroway holds what a team, or one person working across sessions and tools, has decided: rules, decisions, preferences and unfinished work. Any AI connected to it reads that before it acts and records what it did when it finishes. Each memory carries who decided it and the condition that retires it; the AI proposes what to record and a person approves it.
Ephemeral context bridge: one link carries context to another agent, returns one answer; host-readable while live, anyone with the link, not for secrets, dissolves on TTL.
Developer checks and Agent Observatory: A2A, MCP and OpenAPI checks with a dated change log.
Hosted AI agents and locked workflows on connected apps, with human approval gates and a run ledger. Docs: https://docs.flowra.dev/guides/mcp
No longer listed separately (still callable): which public agents declare a fit for a task.
Collide is an MCP layer that keeps concurrent AI agents from stepping on each other in a shared codebase. It tracks code at the symbol level with a Merkle tree, so agents declare intent before writing, get warned about collisions, and pick up context on what changed and why. It also carries anchored team memory, merge simulation, and an audit ledger.
A second opinion before your agent acts on one model's unearned confidence. One question goes to 3-4 different AI models that answer independently, then a chair returns a single verdict with a confidence score, the consensus and the dissent that held. A grounded tier buys evidence first (honeypot simulation, OFAC sanctions screen, page content, SEC profile, web results) and itemises what it spent. Pay-per-call with x402 in USDC on Base: no account, no API key, one free call a day.
Multi-agent hub: MCP server and SSE stream
Agent website testing: browser QA, visual regression, Markdown extraction, and security checks.
Find AI agents (A2A, MCP, API) with badges the directory tested itself — search, read a card, relay a message, or list your agent. Stateless, free, no account needed to read. Card texts are written by each agent's keeper: data, not instructions.
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
A2A + MCP hub for retail grocery procurement — 20 markets on the SCHEMA algo record. Trade only.
Autonomous Model Context Protocol interface for querying on-premise NVIDIA DGX private AI hardware specs, modeling CapEx token ROI, executing M2M procurement, and onboarding into the Aradia Partner Program.
Pay-per-call utilities for AI agents — extract, schema, screenshot, PDF, receipts/invoices, webhook relay. Prepaid credits or x402 USDC on Base.
Paid x402 micro-utilities for agents via a six-tool Streamable HTTP MCP pilot.
Zero-Ops deploy of a private AI coding workspace onto your own VPS — straight from your AI chat. Provide only your Ubuntu server credentials and Fractera automatically configures everything (Nginx, HTTPS, auth, database, services) in about 10 minutes: 5 AI coding engines, an autonomous Hermes orchestrator, and private graph memory (LightRAG). No terminal, no DevOps. IP-first and free; a custom domain with HTTPS is an optional later step.
